1 /* Test of conversion to UTF-16 from legacy encodings.
2 Copyright (C) 2007 Free Software Foundation, Inc.
4 This program is free software; you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 2, or (at your option)
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
14 You should have received a copy of the GNU General Public License
15 along with this program; if not, write to the Free Software Foundation,
16 Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
18 /* Written by Bruno Haible <bruno@clisp.org>, 2007. */
32 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
33 #define ASSERT(expr) \
38 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
44 /* Magic number for detecting bounds violations. */
45 #define MAGIC 0x1983EFF1
48 new_offsets (size_t n)
50 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
58 static enum iconv_ilseq_handler handlers[] =
59 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
65 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
66 ISO-8859-2, and UTF-8. */
68 /* Test conversion from ISO-8859-1 to UTF-16 with no errors. */
69 for (h = 0; h < SIZEOF (handlers); h++)
71 enum iconv_ilseq_handler handler = handlers[h];
72 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
73 static const uint16_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
75 0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
76 'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
77 'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF
79 for (o = 0; o < 2; o++)
81 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
82 uint16_t *result = NULL;
84 int retval = u16_conv_from_encoding ("ISO-8859-1", handler,
85 input, strlen (input),
89 ASSERT (length == SIZEOF (expected));
90 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
93 for (i = 0; i < 37; i++)
94 ASSERT (offsets[i] == i);
95 ASSERT (offsets[37] == MAGIC);
102 /* Test conversion from ISO-8859-2 to UTF-16 with no errors. */
103 for (h = 0; h < SIZEOF (handlers); h++)
105 enum iconv_ilseq_handler handler = handlers[h];
106 static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
107 static const uint16_t expected[] =
109 'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
112 for (o = 0; o < 2; o++)
114 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
115 uint16_t *result = NULL;
117 int retval = u16_conv_from_encoding ("ISO-8859-2", handler,
118 input, strlen (input),
121 ASSERT (retval == 0);
122 ASSERT (length == SIZEOF (expected));
123 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
126 for (i = 0; i < 16; i++)
127 ASSERT (offsets[i] == i);
128 ASSERT (offsets[16] == MAGIC);
135 /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2. */
136 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__)
137 /* Test conversions from autodetect_jp to UTF-16. */
138 for (h = 0; h < SIZEOF (handlers); h++)
140 enum iconv_ilseq_handler handler = handlers[h];
141 static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
142 static const uint16_t expected[] = /* こんにちは */
144 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
146 for (o = 0; o < 2; o++)
148 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
149 uint16_t *result = NULL;
151 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
152 input, strlen (input),
155 ASSERT (retval == 0);
156 ASSERT (length == SIZEOF (expected));
157 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
160 for (i = 0; i < 10; i++)
161 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
162 ASSERT (offsets[10] == MAGIC);
168 for (h = 0; h < SIZEOF (handlers); h++)
170 enum iconv_ilseq_handler handler = handlers[h];
171 static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
172 static const uint16_t expected[] = /* こんにちは */
174 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
176 for (o = 0; o < 2; o++)
178 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
179 uint16_t *result = NULL;
181 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
182 input, strlen (input),
185 ASSERT (retval == 0);
186 ASSERT (length == SIZEOF (expected));
187 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
190 for (i = 0; i < 10; i++)
191 ASSERT (offsets[i] == ((i % 2) == 0 ? i / 2 : (size_t)(-1)));
192 ASSERT (offsets[10] == MAGIC);
198 for (h = 0; h < SIZEOF (handlers); h++)
200 enum iconv_ilseq_handler handler = handlers[h];
201 static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
202 static const uint16_t expected[] = /* こんにちは */
204 0x3053, 0x3093, 0x306B, 0x3061, 0x306F
206 for (o = 0; o < 2; o++)
208 size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
209 uint16_t *result = NULL;
211 int retval = u16_conv_from_encoding ("autodetect_jp", handler,
212 input, strlen (input),
215 ASSERT (retval == 0);
216 ASSERT (length == SIZEOF (expected));
217 ASSERT (result != NULL && u16_cmp (result, expected, SIZEOF (expected)) == 0);
220 for (i = 0; i < 16; i++)
221 ASSERT (offsets[i] == (i == 0 ? 0 :
228 ASSERT (offsets[16] == MAGIC);